© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 28907
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variable names in equations

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    fnlp/Llama-Scope-R1-Distill/400M-Slimpajama-400M-OpenR1-Math-220k/L21R
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Hzfinfdu/SlimPajama-3B and open-r1/OpenR1-Math-220k
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izi
    -0.06
    infeld
    -0.06
    uzu
    -0.06
    raf
    -0.06
    xic
    -0.06
    fee
    -0.06
    757
    -0.06
    kea
    -0.05
    rello
    -0.05
    ói
    -0.05
    POSITIVE LOGITS
    694
    0.07
    ιβ
    0.07
    agus
    0.07
    ez
    0.06
    sand
    0.06
    esModule
    0.06
    _DECREF
    0.06
    ippers
    0.06
    uÄį
    0.06
    artz
    0.06
    Activations Density 0.046%

    No Known Activations